dex

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description does add real value by disclosing what the kotlin action surfaces (raw metadata, suspend/inline info, JVM signatures, coroutine/Compose candidates, JavascriptInterface declarations). It still says nothing about limits, expected inputs existing on disk, or behavior when the mapping file is absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and free of filler, but the semicolon-separated fragments are not front-loaded and read as compressed notes rather than a sentence an agent can parse. Density here hurts comprehension more than it saves size.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter tool with zero schema descriptions and no output schema, the description covers only a fraction of what an agent needs: which action consumes which parameters, what a 'reference' result looks like, and what the kotlin mode requires are all missing. The annotations handle safety but not the operational gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across seven parameters, so the description must carry that burden and largely does not. It hints that mappingPath applies to the class and method actions and implicitly ties className/methodName to class/method lookups, but query, action-selection semantics, and overloadIndex are entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

'精确DEX类/方法/引用' gives a verb-plus-resource shape covering the class, method and references actions, and the kotlin clause names concrete artifacts (suspend/inline signatures, Compose candidates, JavascriptInterface declarations). But the framing is telegraphic and never says what distinguishes this from siblings such as search, framework, decode or native, so an agent must guess where DEX inspection ends and the other tools begin.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage instruction is the fragment 'class/method可用mappingPath', which is a parameter hint rather than a routing rule. Nothing states when to pick 'classes' versus 'class' versus 'references', which action requires className or methodName, or when a sibling tool would be the better choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.